{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T22:34:16Z","timestamp":1783463656300,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":229,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-19-56151"],"award-info":[{"award-number":["IIS-19-56151"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-21-C0165"],"award-info":[{"award-number":["HR0011-21-C0165"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3736557","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T20:52:41Z","timestamp":1754254361000},"page":"6032-6042","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Retrieval And Structuring Augmented Generation with Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9925-3777","authenticated-orcid":false,"given":"Pengcheng","family":"Jiang","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1331-424X","authenticated-orcid":false,"given":"Siru","family":"Ouyang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0509-8652","authenticated-orcid":false,"given":"Yizhu","family":"Jiao","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5728-0224","authenticated-orcid":false,"given":"Ming","family":"Zhong","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7885-1490","authenticated-orcid":false,"given":"Runchu","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3629-2696","authenticated-orcid":false,"given":"Jiawei","family":"Han","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Josh Achiam et al. 2023. Gpt-4 technical report. arXiv:2303.08774(2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Litsearch: A retrieval benchmark for scientific literature search. arXiv:2407.18940(2024).","author":"Anirudh Ajith","year":"2024","unstructured":"Anirudh Ajith et al., 2024. Litsearch: A retrieval benchmark for scientific literature search. arXiv:2407.18940(2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes. VLDB Endow.","volume":"17","author":"Simran","year":"2023","unstructured":"Simran Arora et al., 2023. Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes. VLDB Endow., Vol. 17, 2 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Self-rag: Learning to retrieve, generate, and critique through self-reflection. In ICLR.","author":"Akari Asai","year":"2023","unstructured":"Akari Asai et al., 2023. Self-rag: Learning to retrieve, generate, and critique through self-reflection. In ICLR."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Siddhartha Banerjee et al. 2019. Hierarchical Transfer Learning for Multi-label Text Classification. In ACL.","DOI":"10.18653\/v1\/P19-1633"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Maciej Besta et al. 2024. Graph of Thoughts: Solving Elaborate Problems with Large Language Models. AAAI(Mar. 2024).","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"e_1_3_2_1_7_1","unstructured":"Vladimir Blagojevi et al. 2023. Enhancing rag pipelines in haystack: Introducing diversityranker and lostinthemiddleranker."},{"key":"e_1_3_2_1_8_1","volume-title":"Inpars: Data augmentation for information retrieval using large language models. arXiv:2202.05144(2022).","author":"Luiz Bonifacio","year":"2022","unstructured":"Luiz Bonifacio et al., 2022. Inpars: Data augmentation for information retrieval using large language models. arXiv:2202.05144(2022)."},{"key":"e_1_3_2_1_9_1","unstructured":"Sebastian Borgeaud et al. 2022. Improving language models by retrieving from trillions of tokens. In ICML. PMLR."},{"key":"e_1_3_2_1_10_1","volume-title":"NeurIPS","volume":"33","author":"Tom","year":"2020","unstructured":"Tom Brown et al., 2020a. Language models are few-shot learners. NeurIPS, Vol. 33 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"Brown et al","author":"Tom B.","year":"2020","unstructured":"Tom B. Brown et al., 2020b. Language Models are Few-Shot Learners. In NeurIPS."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Aditi Chaudhary et al. 2019. A Little Annotation does a Lot of Good: A Study in Bootstrapping Low-resource Named Entity Recognizers. In EMNLP-IJCNLP.","DOI":"10.18653\/v1\/D19-1520"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Haibin Chen et al. 2021. Hierarchy-aware Label Semantics Matching Network for Hierarchical Text Classification. In ACL-IJCNLP.","DOI":"10.18653\/v1\/2021.acl-long.337"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Jiawei Chen et al. 2022. Few-shot Named Entity Recognition with Self-describing Networks. In ACL.","DOI":"10.18653\/v1\/2022.acl-long.392"},{"key":"e_1_3_2_1_15_1","unstructured":"Jiao Chen et al. 2023. Knowledge graph completion models are few-shot learners: An empirical study of relation labeling in e-commerce with llms. arXiv:2305.09858(2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"AAAI","volume":"38","author":"Jiawei","unstructured":"Jiawei Chen et al., 2024a. Benchmarking large language models in retrieval-augmented generation. In AAAI, Vol. 38."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Tong Chen et al. 2024b. Dense x retrieval: What retrieval granularity should we use?. In EMNLP.","DOI":"10.18653\/v1\/2024.emnlp-main.845"},{"key":"e_1_3_2_1_18_1","volume-title":"NeurIPS","volume":"36","author":"Xin","year":"2023","unstructured":"Xin Cheng et al., 2023. Lift yourself up: Retrieval-augmented text generation with self-memory. NeurIPS, Vol. 36 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Yew Ken Chia et al. 2022. RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction. In ACL Findings.","DOI":"10.18653\/v1\/2022.findings-acl.5"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Nadezhda Chirkova et al. 2024. Retrieval-augmented generation in multilingual settings. KnowLLM in ACL(2024).","DOI":"10.18653\/v1\/2024.knowllm-1.15"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Eunsol Choi et al. 2018. Ultra-Fine Entity Typing. In ACL.","DOI":"10.18653\/v1\/P18-1009"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Robert Churchill et al. 2022. A Guided Topic-Noise Model for Short Texts. In WWW.","DOI":"10.1145\/3485447.3512007"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"John Dagdelen et al. 2024. Structured information extraction from scientific text with large language models. Nature Communications(2024).","DOI":"10.1038\/s41467-024-45563-x"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Hongliang Dai et al. 2021. Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model. In ACL.","DOI":"10.1162\/tacl_a_00479"},{"key":"e_1_3_2_1_25_1","unstructured":"Zhuyun Dai et al. 2019. Context-aware sentence\/passage term importance estimation for first stage retrieval. arXiv:1910.10687(2019)."},{"key":"e_1_3_2_1_26_1","unstructured":"DeepSeek- and othersAI. 2024. DeepSeek-V3 Technical Report. CoRR Vol. abs\/2412.19437 (2024). arXiv:2412.19437 doi:10.48550\/ARXIV.2412.19437"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.12948"},{"key":"e_1_3_2_1_28_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT.","author":"Jacob Devlin","year":"2019","unstructured":"Jacob Devlin et al., 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT."},{"key":"e_1_3_2_1_29_1","volume-title":"Dieng et al","author":"Adji B.","year":"2020","unstructured":"Adji B. Dieng et al., 2020. Topic Modeling in Embedding Spaces. TACL(2020)."},{"key":"e_1_3_2_1_30_1","unstructured":"Jiannan Dong et al. 2023. Self-Refine: Iterative Refinement with GPT-4. arXiv:2303.17651(2023)."},{"key":"e_1_3_2_1_31_1","unstructured":"Darren Edge et al. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv:2404.16130(2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"Vse: Improving visual-semantic embeddings with hard negatives. arXiv:1707.05612(2017).","author":"Fartash Faghri","year":"2017","unstructured":"Fartash Faghri et al., 2017. Vse: Improving visual-semantic embeddings with hard negatives. arXiv:1707.05612(2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Yan Fang et al. 2024. Scaling laws for dense retrieval. In SIGIR.","DOI":"10.1145\/3626772.3657743"},{"key":"e_1_3_2_1_34_1","volume-title":"Graph: Encoding Graphs for Large Language Models. In ICLR.","author":"Bahare Fatemi","year":"2024","unstructured":"Bahare Fatemi et al., 2024. Talk like a Graph: Encoding Graphs for Large Language Models. In ICLR."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Yanlin Feng et al. 2020. Scalable multi-hop relational reasoning for knowledge-aware question answering. EMNLP(2020).","DOI":"10.18653\/v1\/2020.emnlp-main.99"},{"key":"e_1_3_2_1_36_1","unstructured":"Matthias Fey et al. 2023. Relational deep learning: Graph representation learning on relational databases. arXiv:2312.04615(2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Thibault Formal et al. 2021. SPLADE v2: Sparse lexical and expansion model for information retrieval. (2021).","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_38_1","unstructured":"Chunjing Gan et al. 2023. Making Large Language Models Better Knowledge Miners for Online Marketing with Progressive Prompting Augmentation. arXiv:2312.05276(2023)."},{"key":"e_1_3_2_1_39_1","unstructured":"Jingtong Gao et al. 2024. Llm-enhanced reranking in recommender systems. arXiv:2406.12433(2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Luyu Gao et al. 2021. Complement lexical retrieval model with semantic residual embeddings. In ECIR. Springer.","DOI":"10.1007\/978-3-030-72113-8_10"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Luyu Gao et al. 2022. Unsupervised corpus aware language model pre-training for dense passage retrieval. In ACL.","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"e_1_3_2_1_42_1","unstructured":"Yunfan Gao et al. 2023. Retrieval-augmented generation for large language models: A survey. arXiv:2312.10997 Vol. 2 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Shijie Geng et al. 2022. Improving personalized explanation generation through visualization. In ACL.","DOI":"10.18653\/v1\/2022.acl-long.20"},{"key":"e_1_3_2_1_44_1","volume-title":"Hipporag: Neurobiologically inspired long-term memory for large language models. In NeurIPS.","author":"Guti\u00e9","year":"2024","unstructured":"Guti\u00e9 and others. 2024. Hipporag: Neurobiologically inspired long-term memory for large language models. In NeurIPS."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Kailash A Hambarde et al. 2023. Information retrieval: recent advances and beyond. IEEE Access(2023).","DOI":"10.1109\/ACCESS.2023.3295776"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Bahareh Harandizadeh et al. 2022. Keyword Assisted Embedded Topic Model. In WSDM.","DOI":"10.1145\/3488560.3498518"},{"key":"e_1_3_2_1_47_1","volume-title":"Haveliwala et al","author":"Taher H.","year":"2002","unstructured":"Taher H. Haveliwala et al., 2002. Topic-sensitive PageRank. In WWW."},{"key":"e_1_3_2_1_48_1","unstructured":"Shirley Anugrah Hayati et al. 2018. Retrieval-based neural code generation. In EMNLP."},{"key":"e_1_3_2_1_49_1","volume-title":"NeurIPS","volume":"37","author":"Xiaoxin","year":"2025","unstructured":"Xiaoxin He et al., 2025. G-retriever: Retrieval-augmented generation for textual graph understanding and question answering. NeurIPS, Vol. 37 (2025)."},{"key":"e_1_3_2_1_50_1","unstructured":"Wilbert Jan Heeringa et al. 2004. Measuring dialect pronunciation differences using Levenshtein distance. (2004)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Jiaxin Huang et al. 2020a. CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring. In KDD.","DOI":"10.1145\/3394486.3403244"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Jiaxin Huang et al. 2020b. Guiding Corpus-based Set Expansion by Auxiliary Sets Generation and Co-Expansion. In WWW.","DOI":"10.1145\/3366423.3380284"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Jiaxin Huang et al. 2022. Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation. In KDD.","DOI":"10.1145\/3534678.3539443"},{"key":"e_1_3_2_1_54_1","volume-title":"ACM TIS","volume":"43","author":"Lei","year":"2025","unstructured":"Lei Huang et al., 2025. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM TIS, Vol. 43, 2 (2025)."},{"key":"e_1_3_2_1_55_1","volume-title":"REBEL: Relation Extraction By End-to-end Language generation. In EMNLP Findings.","author":"Pere-Llu\u00eds Huguet","year":"2021","unstructured":"Pere-Llu\u00eds Huguet Cabot and Roberto Navigli. 2021. REBEL: Relation Extraction By End-to-end Language generation. In EMNLP Findings."},{"key":"e_1_3_2_1_56_1","unstructured":"Gautier Izacard et al. 2021. Unsupervised dense information retrieval with contrastive learning. arXiv:2112.09118(2021)."},{"key":"e_1_3_2_1_57_1","volume-title":"Atlas: Few-shot learning with retrieval augmented language models. JMLR(2023).","author":"Gautier Izacard","year":"2023","unstructured":"Gautier Izacard et al., 2023. Atlas: Few-shot learning with retrieval augmented language models. JMLR(2023)."},{"key":"e_1_3_2_1_58_1","unstructured":"Ziwei Ji et al. 2023. Survey of hallucination in natural language generation. ACM computing surveys(2023)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"crossref","unstructured":"Jinhao Jiang et al. 2023a. StructGPT: A General Framework for Large Language Model to Reason over Structured Data. In EMNLP Houda Bouamor et al.(Eds.).","DOI":"10.18653\/v1\/2023.emnlp-main.574"},{"key":"e_1_3_2_1_60_1","unstructured":"Jinhao Jiang et al. 2023b. UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph. In ICLR."},{"key":"e_1_3_2_1_61_1","unstructured":"Pengcheng Jiang et al. 2023c. MedKG: Empowering Medical Education with Interactive Construction and Visualization of Knowledge Graphs via Large Language Models. Preprint(2023)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","unstructured":"Pengcheng Jiang et al. 2023d. Text Augmented Open Knowledge Graph Completion via Pre-Trained Language Models. In Findings of ACL.","DOI":"10.18653\/v1\/2023.findings-acl.709"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Pengcheng Jiang et al. 2024. GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language Models. In NAACL. Association for Computational Linguistics Mexico City Mexico.","DOI":"10.18653\/v1\/2024.naacl-long.155"},{"key":"e_1_3_2_1_64_1","volume-title":"Deepretrieval: Hacking real search engines and retrievers with large language models via reinforcement learning. arXiv:2503.00223(2025).","author":"Pengcheng Jiang","year":"2025","unstructured":"Pengcheng Jiang et al., 2025 a. Deepretrieval: Hacking real search engines and retrievers with large language models via reinforcement learning. arXiv:2503.00223(2025)."},{"key":"e_1_3_2_1_65_1","volume-title":"Kg-fit: Knowledge graph fine-tuning upon open-world knowledge. NeurIPS(2025).","author":"Pengcheng Jiang","year":"2025","unstructured":"Pengcheng Jiang et al., 2025 b. Kg-fit: Knowledge graph fine-tuning upon open-world knowledge. NeurIPS(2025)."},{"key":"e_1_3_2_1_66_1","unstructured":"Pengcheng Jiang et al. 2025 c. Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval. In ICLR."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"crossref","unstructured":"Zhengbao Jiang et al. 2023 e. Active retrieval augmented generation. In EMNLP.","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Yizhu Jiao et al. 2022. Open-Vocabulary Argument Role Prediction For Event Extraction. In EMNLP Findings.","DOI":"10.18653\/v1\/2022.findings-emnlp.395"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"crossref","unstructured":"Yizhu Jiao et al. 2023. Instruct and Extract: Instruction Tuning for On-Demand Information Extraction. In EMNLP.","DOI":"10.18653\/v1\/2023.emnlp-main.620"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","unstructured":"Yizhu Jiao et al. 2024. Text2DB: Integration-Aware Information Extraction with Large Language Model Agents. In ACL Findings.","DOI":"10.18653\/v1\/2024.findings-acl.12"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.01763"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"crossref","unstructured":"Hao Kang et al. 2025. Interpret and Control Dense Retrieval with Sparse Latent Features. In NAACL.","DOI":"10.18653\/v1\/2025.naacl-short.58"},{"key":"e_1_3_2_1_73_1","unstructured":"Minki Kang et al. 2023. Knowledge graph-augmented language models for knowledge-grounded dialogue generation. arXiv:2305.18846(2023)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"crossref","unstructured":"SeongKu Kang et al. 2024a. Improving retrieval in theme-specific applications using a corpus topical taxonomy. In WWW.","DOI":"10.1145\/3589334.3645512"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"crossref","unstructured":"SeongKu Kang et al. 2024b. Taxonomy-guided Semantic Indexing for Academic Paper Search. In EMNLP.","DOI":"10.18653\/v1\/2024.emnlp-main.407"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"crossref","unstructured":"Priyanka Kargupta et al. 2025. Unsupervised Episode Detection for Large-Scale News Events. In ACL.","DOI":"10.18653\/v1\/2025.acl-long.1433"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"crossref","unstructured":"Md Rezaul Karim et al. 2023. From Large Language Models to Knowledge Graphs for Biomarker Discovery in Cancer. arXiv:2310.08365(2023).","DOI":"10.24251\/HICSS.2024.670"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"crossref","unstructured":"Vladimir Karpukhin et al. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In EMNLP.","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_79_1","volume-title":"Proceedings of the 43rd International ACM SIGIR.","author":"Omar","unstructured":"Omar Khattab et al., 2020. Colbert: Efficient and effective passage search via contextualized late interaction over bert. In Proceedings of the 43rd International ACM SIGIR."},{"key":"e_1_3_2_1_80_1","volume-title":"Demonstrate-search-predict: Composing retrieval and language models for knowledge-intensive nlp. arXiv:2212.14024(2022).","author":"Omar Khattab","year":"2022","unstructured":"Omar Khattab et al., 2022. Demonstrate-search-predict: Composing retrieval and language models for knowledge-intensive nlp. arXiv:2212.14024(2022)."},{"key":"e_1_3_2_1_81_1","unstructured":"Gangwoo Kim et al. 2023. Tree of clarifications: Answering ambiguous questions with retrieval-augmented large language models. In EMNLP."},{"key":"e_1_3_2_1_82_1","unstructured":"Tanay Komarlu et al. 2024. OntoType: Ontology-Guided Zero-Shot Fine-Grained Entity Typing with Weak Supervision from Pre-Trained Language Models. In KDD."},{"key":"e_1_3_2_1_83_1","unstructured":"Rajasekar Krishnamurthy et al. 2006. Avatar information extraction system. (2006)."},{"key":"e_1_3_2_1_84_1","unstructured":"Dongha Lee et al. 2022. TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters. In WWW."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"crossref","unstructured":"Elena Leitner et al. 2019. Fine-grained named entity recognition in legal documents. In SEMANTICS. Springer.","DOI":"10.1007\/978-3-030-33220-4_20"},{"key":"e_1_3_2_1_86_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL.","author":"Mike Lewis","year":"2020","unstructured":"Mike Lewis et al., 2020a. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL."},{"key":"e_1_3_2_1_87_1","volume-title":"NeurIPS","volume":"33","author":"Patrick","year":"2020","unstructured":"Patrick Lewis et al., 2020b. Retrieval-augmented generation for knowledge-intensive nlp tasks. NeurIPS, Vol. 33 (2020)."},{"key":"e_1_3_2_1_88_1","volume-title":"TACL","volume":"10","author":"Bangzheng","year":"2022","unstructured":"Bangzheng Li et al., 2022a. Ultra-fine entity typing with indirect supervision from natural language inference. TACL, Vol. 10 (2022)."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"crossref","unstructured":"Guozheng Li et al. 2023a. Revisiting large language models as zero-shot relation extractors. In EMNLP Findings.","DOI":"10.18653\/v1\/2023.findings-acl.50"},{"key":"e_1_3_2_1_90_1","unstructured":"Junpeng Li et al. 2021. Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models. In EMNLP Houda Bouamor Juan Pino and Kalika Bali(Eds.)."},{"key":"e_1_3_2_1_91_1","unstructured":"Jing Li et al. 2020. A survey on deep learning for named entity recognition. TKDE(2020)."},{"key":"e_1_3_2_1_92_1","volume-title":"NeurIPS","volume":"36","author":"Jinyang","year":"2023","unstructured":"Jinyang Li et al., 2023b. Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls. NeurIPS, Vol. 36 (2023)."},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"crossref","unstructured":"Na Li et al. 2023c. Ultra-fine entity typing with prior knowledge about labels: A simple clustering based strategy. arXiv:2305.12802(2023).","DOI":"10.18653\/v1\/2023.findings-emnlp.786"},{"key":"e_1_3_2_1_94_1","volume-title":"Table-gpt: Table-tuned gpt for diverse table tasks. arXiv:2310.09263(2023).","author":"Peng Li","year":"2023","unstructured":"Peng Li et al., 2023d. Table-gpt: Table-tuned gpt for diverse table tasks. arXiv:2310.09263(2023)."},{"key":"e_1_3_2_1_95_1","unstructured":"Xiaoxi Li et al. 2024. From matching to generation: A survey on generative information retrieval. arXiv:2404.14851(2024)."},{"key":"e_1_3_2_1_96_1","unstructured":"Yinghui Li et al. 2022b. Contrastive Learning with Hard Negative Entities for Entity Set Expansion. In SIGIR."},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"crossref","unstructured":"Zijing Liang et al. 2024. A Survey of Multimodel Large Language Models. In CAICE.","DOI":"10.1145\/3672758.3672824"},{"key":"e_1_3_2_1_98_1","unstructured":"Jimmy Lin et al. 2021. A few brief notes on deepimpact coil and a conceptual framework for information retrieval techniques. arXiv:2106.14807(2021)."},{"key":"e_1_3_2_1_99_1","unstructured":"Xi Victoria Lin et al. 2020. Bridging textual and tabular data for cross-domain text-to-SQL semantic parsing. In EMNLP Findings."},{"key":"e_1_3_2_1_100_1","volume-title":"TKDE","volume":"16","author":"Fang","year":"2004","unstructured":"Fang Liu et al., 2004. Personalized web search for improving retrieval effectiveness. TKDE, Vol. 16, 1 (2004)."},{"key":"e_1_3_2_1_101_1","volume-title":"TACL","volume":"12","author":"Nelson F","year":"2024","unstructured":"Nelson F Liu et al., 2024. Lost in the middle: How language models use long contexts. TACL, Vol. 12 (2024)."},{"key":"e_1_3_2_1_102_1","unstructured":"Runxuan Liu et al. 2025. Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering. arXiv:2502.11491(2025)."},{"key":"e_1_3_2_1_103_1","volume-title":"Kg-bart: Knowledge graph-augmented bart for generative commonsense reasoning. In AAAI.","author":"Ye Liu","year":"2021","unstructured":"Ye Liu et al., 2021. Kg-bart: Knowledge graph-augmented bart for generative commonsense reasoning. In AAAI."},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"crossref","unstructured":"Yi Luan et al. 2021. Sparse dense and attentional representations for text retrieval. TACL(2021).","DOI":"10.1162\/tacl_a_00369"},{"key":"e_1_3_2_1_105_1","volume-title":"Chatrule: Mining logical rules with large language models for knowledge graph reasoning. arXiv:2309.01538(2023).","author":"Linhao Luo","year":"2023","unstructured":"Linhao Luo et al., 2023a. Chatrule: Mining logical rules with large language models for knowledge graph reasoning. arXiv:2309.01538(2023)."},{"key":"e_1_3_2_1_106_1","volume-title":"Graphs: Faithful and Interpretable Large Language Model Reasoning. In ICLR.","author":"Linhao Luo","year":"2024","unstructured":"Linhao Luo et al., 2024. Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. In ICLR."},{"key":"e_1_3_2_1_107_1","unstructured":"Linhao Luo et al. 2025. GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation. arXiv:2502.01113(2025)."},{"key":"e_1_3_2_1_108_1","unstructured":"Ziyang Luo et al. 2023b. Augmented large language models with parametric knowledge guiding. arXiv:2305.04757(2023)."},{"key":"e_1_3_2_1_109_1","unstructured":"Yuanhua Lv et al. 2011a. Adaptive Term Frequency Normalization for BM25. In CIKM."},{"key":"e_1_3_2_1_110_1","unstructured":"Yuanhua Lv et al. 2011b. Lower-bounding term frequency normalization. In CIKM."},{"key":"e_1_3_2_1_111_1","unstructured":"Shengjie Ma et al. 2025. Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation. In ICLR."},{"key":"e_1_3_2_1_112_1","unstructured":"Xinbei Ma et al. 2023a. Query rewriting in retrieval-augmented large language models. In EMNLP."},{"key":"e_1_3_2_1_113_1","unstructured":"Yubo Ma et al. 2023b. Large language model is not a good few-shot information extractor but a good reranker for hard samples!. In EMNLP Findings."},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"crossref","unstructured":"Yu Meng et al. 2018. Weakly-Supervised Neural Text Classification. In CIKM.","DOI":"10.1145\/3269206.3271737"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"crossref","unstructured":"Yu Meng et al. 2019. Weakly-supervised hierarchical text classification. In AAAI.","DOI":"10.1007\/978-3-031-01914-2_5"},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"crossref","unstructured":"Yu Meng et al. 2020a. Discriminative Topic Mining via Category-Name Guided Text Embedding. In WWW.","DOI":"10.1145\/3366423.3380278"},{"key":"e_1_3_2_1_117_1","doi-asserted-by":"crossref","unstructured":"Yu Meng et al. 2020b. Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding. In KDD.","DOI":"10.1145\/3394486.3403242"},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"crossref","unstructured":"Yu Meng et al. 2020c. Text Classification Using Label Names Only: A Language Model Self-Training Approach. In EMNLP.","DOI":"10.18653\/v1\/2020.emnlp-main.724"},{"key":"e_1_3_2_1_119_1","doi-asserted-by":"crossref","unstructured":"Yu Meng et al. 2021. Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training. In EMNLP.","DOI":"10.18653\/v1\/2021.emnlp-main.810"},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"crossref","unstructured":"Yu Meng et al. 2022. Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations. In WWW.","DOI":"10.1145\/3485447.3512034"},{"key":"e_1_3_2_1_121_1","unstructured":"Gr\u00e9 and others Mialon. 2023. Augmented language models: a survey. arXiv:2302.07842(2023)."},{"key":"e_1_3_2_1_122_1","unstructured":"Tomas Mikolov et al. 2013. Efficient estimation of word representations in vector space. arXiv:1301.3781(2013)."},{"key":"e_1_3_2_1_123_1","unstructured":"Sewon Min et al. 2021. Noisy channel language model prompting for few-shot text classification. arXiv:2108.04106(2021)."},{"key":"e_1_3_2_1_124_1","doi-asserted-by":"crossref","unstructured":"Seyed Abbas Momtazi et al. 2010. Hierarchical Pitman-Yor Language Model for Information Retrieval. In SIGIR.","DOI":"10.1145\/1835449.1835619"},{"key":"e_1_3_2_1_125_1","volume-title":"ECIR","author":"Shahrzad","year":"2021","unstructured":"Shahrzad Naseri et al., 2021. Ceqe: Contextualized embeddings for query expansion. In ECIR 2021. Springer."},{"key":"e_1_3_2_1_126_1","unstructured":"Tri Nguyen et al. 2016. Ms marco: A human-generated machine reading comprehension dataset. (2016)."},{"key":"e_1_3_2_1_127_1","unstructured":"Jianmo Ni et al. 2022. Large dual encoders are generalizable retrievers. EMNLP(2022)."},{"key":"e_1_3_2_1_128_1","unstructured":"Rodrigo Nogueira et al. 2019a. Document expansion by query prediction. arXiv:1904.08375(2019)."},{"key":"e_1_3_2_1_129_1","unstructured":"Rodrigo Nogueira et al. 2019b. From doc2query to docTTTTTquery. Online preprint Vol. 6 2 (2019)."},{"key":"e_1_3_2_1_130_1","unstructured":"Rodrigo Nogueira et al. 2019c. Passage Re-ranking with BERT. arXiv:1901.04085(2019)."},{"key":"e_1_3_2_1_131_1","unstructured":"Zach Nussbaum et al. 2024. Nomic embed: Training a reproducible long context text embedder. arXiv:2402.01613(2024)."},{"key":"e_1_3_2_1_132_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5511"},{"key":"e_1_3_2_1_133_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.16720"},{"key":"e_1_3_2_1_134_1","volume-title":"NeurIPS","volume":"35","author":"Long","year":"2022","unstructured":"Long Ouyang et al., 2022a. Training language models to follow instructions with human feedback. NeurIPS, Vol. 35 (2022)."},{"key":"e_1_3_2_1_135_1","unstructured":"Long Ouyang et al. 2022b. Training language models to follow instructions with human feedback. In NeurIPS."},{"key":"e_1_3_2_1_136_1","doi-asserted-by":"crossref","unstructured":"Siru Ouyang et al. 2024. Ontology Enrichment for Effective Fine-grained Entity Typing. In KDD.","DOI":"10.1145\/3637528.3671857"},{"key":"e_1_3_2_1_137_1","unstructured":"Oded Ovadia et al. 2023. Fine-tuning or retrieval? comparing knowledge injection in llms. arXiv:2312.05934(2023)."},{"key":"e_1_3_2_1_138_1","unstructured":"Charles Packer et al. 2023. MemGPT: Towards LLMs as Operating Systems. arXiv:2310.08560(2023)."},{"key":"e_1_3_2_1_139_1","volume-title":"TKDE","volume":"36","author":"Shirui","year":"2024","unstructured":"Shirui Pan et al., 2024. Unifying large language models and knowledge graphs: A roadmap. TKDE, Vol. 36, 7 (2024)."},{"key":"e_1_3_2_1_140_1","volume-title":"Proceedings of the 3rd international semantic search workshop.","author":"P\u00e9","year":"2010","unstructured":"P\u00e9 and others. 2010. Using BM25F for semantic search. In Proceedings of the 3rd international semantic search workshop."},{"key":"e_1_3_2_1_141_1","doi-asserted-by":"crossref","unstructured":"Hao Peng et al. 2018. Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN. In WWW.","DOI":"10.1145\/3178876.3186005"},{"key":"e_1_3_2_1_142_1","volume-title":"One-shot: Named Entity Recognition via Extremely Weak Supervision. In EMNLP Findings.","author":"Letian Peng","year":"2023","unstructured":"Letian Peng et al., 2023. Less than One-shot: Named Entity Recognition via Extremely Weak Supervision. In EMNLP Findings."},{"key":"e_1_3_2_1_143_1","doi-asserted-by":"crossref","unstructured":"Wenjun Peng et al. 2024. Large language model based long-tail query rewriting in taobao search. In WWW Companion.","DOI":"10.1145\/3589335.3648298"},{"key":"e_1_3_2_1_144_1","volume-title":"Synchromesh: Reliable code generation from pre-trained language models. In ICLR.","author":"Gabriel Poesia","year":"2022","unstructured":"Gabriel Poesia et al., 2022. Synchromesh: Reliable code generation from pre-trained language models. In ICLR."},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"crossref","unstructured":"Jaroslav Pokorny et al. 2004. Web searching and information retrieval. Computing in Science & Engineering(2004).","DOI":"10.1109\/MCSE.2004.24"},{"key":"e_1_3_2_1_146_1","unstructured":"Meng Qu et al. 2018. Weakly-supervised Relation Extraction by Pattern-enhanced Embedding Learning. In WWW."},{"key":"e_1_3_2_1_147_1","unstructured":"Yingqi Qu et al. 2021. RocketQA: An optimized training approach to dense passage retrieval for open-domain question answering. In NAACL."},{"key":"e_1_3_2_1_148_1","unstructured":"Alec Radford et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_149_1","unstructured":"Rafael Rafailov et al. 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. In NeurIPS."},{"key":"e_1_3_2_1_150_1","volume-title":"JMLR","volume":"21","author":"Colin","year":"2020","unstructured":"Colin Raffel et al., 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR, Vol. 21, 140 (2020)."},{"key":"e_1_3_2_1_151_1","volume-title":"Data Programming: Creating Large Training Sets, Quickly. In NeurIPS.","author":"Alexander Ratner","year":"2016","unstructured":"Alexander Ratner et al., 2016. Data Programming: Creating Large Training Sets, Quickly. In NeurIPS."},{"key":"e_1_3_2_1_152_1","doi-asserted-by":"crossref","unstructured":"Stephen E Robertson et al. 1995. Okapi at TREC-3. Nist Special Publication Sp(1995).","DOI":"10.6028\/NIST.SP.500-225.adhoc-city"},{"key":"e_1_3_2_1_153_1","doi-asserted-by":"crossref","unstructured":"Maya Rotmensch et al. 2017. Learning a health knowledge graph from electronic medical records. Scientific reports Vol. 7 1 (2017).","DOI":"10.1038\/s41598-017-05778-z"},{"key":"e_1_3_2_1_154_1","unstructured":"Dwaipayan Roy et al. 2016. Using word embeddings for automatic query expansion. arXiv:1606.07608(2016)."},{"key":"e_1_3_2_1_155_1","doi-asserted-by":"crossref","unstructured":"Oscar Sainz et al. 2021. Label Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction. In EMNLP.","DOI":"10.18653\/v1\/2021.emnlp-main.92"},{"key":"e_1_3_2_1_156_1","volume-title":"Kg-rag: Bridging the gap between knowledge and creativity. arXiv:2405.12035(2024).","author":"Diego Sanmartin","year":"2024","unstructured":"Diego Sanmartin et al., 2024. Kg-rag: Bridging the gap between knowledge and creativity. arXiv:2405.12035(2024)."},{"key":"e_1_3_2_1_157_1","unstructured":"John Schulman et al. 2017. Proximal Policy Optimization Algorithms. arXiv:1707.06347(2017)."},{"key":"e_1_3_2_1_158_1","doi-asserted-by":"crossref","unstructured":"Jingbo Shang et al. 2018. Learning Named Entity Tagger using Domain-Specific Dictionary. In EMNLP.","DOI":"10.18653\/v1\/D18-1230"},{"key":"e_1_3_2_1_159_1","doi-asserted-by":"crossref","unstructured":"Yu-Ming Shang et al. 2025. From local to global: Leveraging document graph for named entity recognition. Knowledge-Based Systems(2025).","DOI":"10.1016\/j.knosys.2025.113017"},{"key":"e_1_3_2_1_160_1","doi-asserted-by":"crossref","unstructured":"Zhihong Shao et al. 2023. Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy. In EMNLP Findings.","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"e_1_3_2_1_161_1","volume-title":"Setexpan: Corpus-based set expansion via context feature selection and rank ensemble. In ECML-PKDD.","author":"Jiaming Shen","year":"2017","unstructured":"Jiaming Shen et al., 2017. Setexpan: Corpus-based set expansion via context feature selection and rank ensemble. In ECML-PKDD."},{"key":"e_1_3_2_1_162_1","volume-title":"Hiexpan: Task-guided taxonomy construction by hierarchical tree expansion. In KDD.","author":"Jiaming Shen","year":"2018","unstructured":"Jiaming Shen et al., 2018. Hiexpan: Task-guided taxonomy construction by hierarchical tree expansion. In KDD."},{"key":"e_1_3_2_1_163_1","doi-asserted-by":"crossref","unstructured":"Jiaming Shen et al. 2021. TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class Names. In NAACL.","DOI":"10.18653\/v1\/2021.naacl-main.335"},{"key":"e_1_3_2_1_164_1","volume-title":"Nature","volume":"620","author":"Karan","year":"2023","unstructured":"Karan Singhal et al., 2023. Large language models encode clinical knowledge. Nature, Vol. 620, 7972 (2023)."},{"key":"e_1_3_2_1_165_1","doi-asserted-by":"crossref","unstructured":"Yangqiu Song et al. 2014. On Dataless Hierarchical Text Classification. In AAAI.","DOI":"10.1609\/aaai.v28i1.8938"},{"key":"e_1_3_2_1_166_1","doi-asserted-by":"crossref","unstructured":"Karen Sparck Jones et al. 1972. A statistical interpretation of term specificity and its application in retrieval. Journal of documentation(1972).","DOI":"10.1108\/eb026526"},{"key":"e_1_3_2_1_167_1","unstructured":"Jiashuo Sun et al. 2024. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. In ICLR."},{"key":"e_1_3_2_1_168_1","unstructured":"Xiaofei Sun et al. 2023. Text Classification via Large Language Models. In EMNLP Findings."},{"key":"e_1_3_2_1_169_1","unstructured":"Yueqing Sun et al. 2022. JointLK: Joint reasoning with language models and knowledge graphs for commonsense question answering. In NAACL."},{"key":"e_1_3_2_1_170_1","unstructured":"Ammar Tahir et al. 2023. Knowledge Graph GPT. https:\/\/github.com\/iAmmarTahir\/KnowledgeGraphGPT."},{"key":"e_1_3_2_1_171_1","volume-title":"NeurIPS","volume":"35","author":"Yi","year":"2022","unstructured":"Yi Tay et al., 2022. Transformer memory as a differentiable search index. NeurIPS, Vol. 35 (2022)."},{"key":"e_1_3_2_1_172_1","unstructured":"Rafael Teixeira de Lima et al. 2025. Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems. In ICCL: Industry Track. Abu Dhabi UAE."},{"key":"e_1_3_2_1_173_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. In NeurIPS Datasets and Benchmark.","author":"Nandan Thakur","year":"2021","unstructured":"Nandan Thakur et al., 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. In NeurIPS Datasets and Benchmark."},{"key":"e_1_3_2_1_174_1","doi-asserted-by":"crossref","unstructured":"Andrew Trotman et al. 2014. Improvements to BM25 and language models examined. In ADCS.","DOI":"10.1145\/2682862.2682863"},{"key":"e_1_3_2_1_175_1","unstructured":"Zhucheng Tu et al. 2022. Leveraging Entity Representations Dense-Sparse Hybrids and Fusion-in-Decoder for Cross-Lingual Question Answering. arXiv:2207.01940(2022)."},{"key":"e_1_3_2_1_176_1","volume-title":"NeurIPS","volume":"30","author":"Ashish","year":"2017","unstructured":"Ashish Vaswani et al., 2017. Attention is all you need. NeurIPS, Vol. 30 (2017)."},{"key":"e_1_3_2_1_177_1","doi-asserted-by":"crossref","unstructured":"Somin Wadhwa et al. 2023. Revisiting Relation Extraction in the era of Large Language Models. In ACL.","DOI":"10.18653\/v1\/2023.acl-long.868"},{"key":"e_1_3_2_1_178_1","doi-asserted-by":"crossref","unstructured":"Zhen Wan et al. 2023. GPT-RE: In-context Learning for Relation Extraction using Large Language Models. In EMNLP.","DOI":"10.18653\/v1\/2023.emnlp-main.214"},{"key":"e_1_3_2_1_179_1","unstructured":"Liang Wang et al. 2022a. Text embeddings by weakly-supervised contrastive pre-training. arXiv:2212.03533(2022)."},{"key":"e_1_3_2_1_180_1","doi-asserted-by":"crossref","unstructured":"Shuohang Wang et al. 2022b. Training data is more valuable than you think: A simple and effective method by retrieving from training data. In ACL.","DOI":"10.18653\/v1\/2022.acl-long.226"},{"key":"e_1_3_2_1_181_1","volume-title":"Gpt-ner: Named entity recognition via large language models. In NAACL Findings.","author":"Shuhe Wang","year":"2023","unstructured":"Shuhe Wang et al., 2023a. Gpt-ner: Named entity recognition via large language models. In NAACL Findings."},{"key":"e_1_3_2_1_182_1","unstructured":"Siyuan Wang et al. 2023b. Unifying Structure Reasoning and Language Pre-Training for Complex Reasoning Tasks. TASLP(2023)."},{"key":"e_1_3_2_1_183_1","doi-asserted-by":"crossref","unstructured":"Xuan Wang et al. 2020. Pattern-enhanced Named Entity Recognition with Distant Supervision. In BigData.","DOI":"10.1109\/BigData50022.2020.9378052"},{"key":"e_1_3_2_1_184_1","volume-title":"Knowledgpt: Enhancing large language models with retrieval and storage access on knowledge bases. arXiv:2308.11761(2023).","author":"Xintao Wang","year":"2023","unstructured":"Xintao Wang et al., 2023c. Knowledgpt: Enhancing large language models with retrieval and storage access on knowledge bases. arXiv:2308.11761(2023)."},{"key":"e_1_3_2_1_185_1","volume-title":"NeurIPS","volume":"35","author":"Yujing","year":"2022","unstructured":"Yujing Wang et al., 2022c. A neural corpus indexer for document retrieval. NeurIPS, Vol. 35 (2022)."},{"key":"e_1_3_2_1_186_1","doi-asserted-by":"crossref","unstructured":"Zihan Wang et al. 2021. X-Class: Text Classification with Extremely Weak Supervision. In NAACL-HLT.","DOI":"10.18653\/v1\/2021.naacl-main.242"},{"key":"e_1_3_2_1_187_1","doi-asserted-by":"crossref","unstructured":"Jonatas Wehrmann et al. 2018. Hierarchical Multi-label Classification Networks. In ICML.","DOI":"10.1145\/3019612.3019664"},{"key":"e_1_3_2_1_188_1","volume-title":"NeurIPS","volume":"35","author":"Jason","year":"2022","unstructured":"Jason Wei et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. NeurIPS, Vol. 35 (2022)."},{"key":"e_1_3_2_1_189_1","volume-title":"Mindmap: Knowledge graph prompting sparks graph of thoughts in large language models. arXiv:2308.09729(2023).","author":"Yilin Wen","year":"2023","unstructured":"Yilin Wen et al., 2023a. Mindmap: Knowledge graph prompting sparks graph of thoughts in large language models. arXiv:2308.09729(2023)."},{"key":"e_1_3_2_1_190_1","doi-asserted-by":"crossref","unstructured":"Zhihao Wen et al. 2023b. Augmenting low-resource text classification with graph-grounded pre-training and prompting. In SIGIR.","DOI":"10.1145\/3539618.3591641"},{"key":"e_1_3_2_1_191_1","doi-asserted-by":"crossref","unstructured":"Jinfeng Xiao et al. 2023. Taxonomy-Guided Fine-Grained Entity Set Expansion. In SDM.","DOI":"10.1137\/1.9781611977653.ch71"},{"key":"e_1_3_2_1_192_1","volume-title":"SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction. In NAACL-HLT.","author":"Yuxin Xiao","year":"2022","unstructured":"Yuxin Xiao et al., 2022. SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction. In NAACL-HLT."},{"key":"e_1_3_2_1_193_1","volume-title":"Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion. In ACL Findings.","author":"Yiqing Xie","year":"2022","unstructured":"Yiqing Xie et al., 2022. Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion. In ACL Findings."},{"key":"e_1_3_2_1_194_1","unstructured":"Lee Xiong et al. 2021. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In ICLR."},{"key":"e_1_3_2_1_195_1","volume-title":"Recomp: Improving retrieval-augmented lms with compression and selective augmentation. ICLR(2024).","author":"Fangyuan Xu","year":"2024","unstructured":"Fangyuan Xu et al., 2024a. Recomp: Improving retrieval-augmented lms with compression and selective augmentation. ICLR(2024)."},{"key":"e_1_3_2_1_196_1","unstructured":"Zhentao Xu et al. 2024b. Retrieval-augmented generation with knowledge graphs for customer service question answering. In SIGIR."},{"key":"e_1_3_2_1_197_1","unstructured":"Hang Yan et al. 2021. A Unified Generative Framework for Aspect-based Sentiment Analysis. In ACL-IJCNLP."},{"key":"e_1_3_2_1_198_1","doi-asserted-by":"crossref","unstructured":"Zichao Yang et al. 2016. Hierarchical Attention Networks for Document Classification. In NAACL.","DOI":"10.18653\/v1\/N16-1174"},{"key":"e_1_3_2_1_199_1","doi-asserted-by":"crossref","unstructured":"Zeng Yang et al. 2022. SEE-Few: Seed Expand and Entail for Few-shot Named Entity Recognition. In COLING.","DOI":"10.18653\/v1\/2023.findings-emnlp.1046"},{"key":"e_1_3_2_1_200_1","doi-asserted-by":"crossref","unstructured":"Michihiro Yasunaga et al. 2021. QA-GNN: Reasoning with language models and knowledge graphs for question answering. NAACL(2021).","DOI":"10.18653\/v1\/2021.naacl-main.45"},{"key":"e_1_3_2_1_201_1","unstructured":"Michihiro Yasunaga et al. 2022. Deep bidirectional language-knowledge graph pretraining. NeurIPS(2022)."},{"key":"e_1_3_2_1_202_1","unstructured":"Changlong Yu et al. 2023. FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery. In ACL Findings."},{"key":"e_1_3_2_1_203_1","unstructured":"Wenhao Yu et al. 2022. Generate rather than retrieve: Large language models are strong context generators. arXiv:2209.10063(2022)."},{"key":"e_1_3_2_1_204_1","unstructured":"Xiangrong Zeng et al. 2018. Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism. In ACL."},{"key":"e_1_3_2_1_205_1","unstructured":"ChengXiang Zhai et al. 2001. A Study of Smoothing Methods for Language Models Applied to Ad Hoc Information Retrieval. In SIGIR."},{"key":"e_1_3_2_1_206_1","doi-asserted-by":"crossref","unstructured":"Chao Zhang et al. 2018. TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering. In KDD.","DOI":"10.1145\/3219819.3220064"},{"key":"e_1_3_2_1_207_1","doi-asserted-by":"crossref","unstructured":"Kai Zhang et al. 2023a. Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors. In Findings of ACL.","DOI":"10.18653\/v1\/2023.findings-acl.50"},{"key":"e_1_3_2_1_208_1","doi-asserted-by":"crossref","unstructured":"Lu Zhang et al. 2021a. Weakly-supervised Text Classification Based on Keyword Graph. In EMNLP.","DOI":"10.18653\/v1\/2021.emnlp-main.222"},{"key":"e_1_3_2_1_209_1","unstructured":"Peitian Zhang et al. 2023b. Retrieve anything to augment large language models. arXiv:2310.07554(2023)."},{"key":"e_1_3_2_1_210_1","unstructured":"Tianshu Zhang et al. 2023c. TableLlama: Towards Open Large Generalist Models for Tables. arXiv:2311.09206(2023)."},{"key":"e_1_3_2_1_211_1","volume-title":"Greaselm: Graph reasoning enhanced language models for question answering. In ICLR.","author":"Xikun Zhang","year":"2022","unstructured":"Xikun Zhang et al., 2022a. Greaselm: Graph reasoning enhanced language models for question answering. In ICLR."},{"key":"e_1_3_2_1_212_1","doi-asserted-by":"crossref","unstructured":"Yunyi Zhang et al. 2020. Empower Entity Set Expansion via Language Model Probing. In ACL.","DOI":"10.18653\/v1\/2020.acl-main.725"},{"key":"e_1_3_2_1_213_1","doi-asserted-by":"crossref","unstructured":"Yu Zhang et al. 2021b. Hierarchical Metadata-Aware Document Categorization under Weak Supervision. In WSDM.","DOI":"10.1145\/3437963.3441730"},{"key":"e_1_3_2_1_214_1","doi-asserted-by":"crossref","unstructured":"Yu Zhang et al. 2022b. Seed-Guided Topic Discovery with Out-of-Vocabulary Seeds. In NAACL.","DOI":"10.18653\/v1\/2022.naacl-main.21"},{"key":"e_1_3_2_1_215_1","doi-asserted-by":"crossref","unstructured":"Yu Zhang et al. 2023d. Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contexts. In WSDM.","DOI":"10.1145\/3539597.3570475"},{"key":"e_1_3_2_1_216_1","doi-asserted-by":"crossref","unstructured":"Yunyi Zhang et al. 2023 e. PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training. In EMNLP.","DOI":"10.18653\/v1\/2023.emnlp-main.780"},{"key":"e_1_3_2_1_217_1","doi-asserted-by":"crossref","unstructured":"Yu Zhang et al. 2024. Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains. AAAI(2024).","DOI":"10.1609\/aaai.v38i17.29933"},{"key":"e_1_3_2_1_218_1","doi-asserted-by":"crossref","unstructured":"Yunyi Zhang et al. 2025. TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision. In WWW.","DOI":"10.1145\/3696410.3714940"},{"key":"e_1_3_2_1_219_1","doi-asserted-by":"crossref","unstructured":"Zihan Zhang et al. 2022c. Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics. In NAACL.","DOI":"10.18653\/v1\/2022.naacl-main.285"},{"key":"e_1_3_2_1_220_1","unstructured":"Siyun Zhao et al. 2024a. Retrieval augmented generation (rag) and beyond: A comprehensive survey on how to make your llms use external data more wisely. arXiv:2409.14924(2024)."},{"key":"e_1_3_2_1_221_1","unstructured":"Wayne Xin Zhao et al. 2024b. Dense text retrieval based on pretrained language models: A survey. ACM TIS(2024)."},{"key":"e_1_3_2_1_222_1","doi-asserted-by":"crossref","unstructured":"Xuandong Zhao et al. 2023. Pre-trained Language Models Can be Fully Zero-Shot Learners. In ACL.","DOI":"10.18653\/v1\/2023.acl-long.869"},{"key":"e_1_3_2_1_223_1","volume-title":"Comput. Surveys","volume":"56","author":"Lingfeng","year":"2023","unstructured":"Lingfeng Zhong et al., 2023. A comprehensive survey on automatic knowledge graph construction. Comput. Surveys, Vol. 56, 4 (2023)."},{"key":"e_1_3_2_1_224_1","doi-asserted-by":"crossref","unstructured":"Ben Zhou et al. 2018. Zero-Shot Open Entity Typing as Type-Compatible Grounding. In EMNLP.","DOI":"10.18653\/v1\/D18-1231"},{"key":"e_1_3_2_1_225_1","doi-asserted-by":"crossref","unstructured":"Sizhe Zhou et al. 2023. Corpus-Based Relation Extraction by Identifying and Refining Relation Patterns. In ECML PKDD.","DOI":"10.1007\/978-3-031-43421-1_2"},{"key":"e_1_3_2_1_226_1","volume-title":"Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction. arXiv:2402.11142(2024).","author":"Sizhe Zhou","year":"2024","unstructured":"Sizhe Zhou et al., 2024a. Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction. arXiv:2402.11142(2024)."},{"key":"e_1_3_2_1_227_1","volume-title":"VLDB Endow.","volume":"17","author":"Xuanhe","year":"2024","unstructured":"Xuanhe Zhou et al., 2024b. D-Bot: Database Diagnosis System using Large Language Models. VLDB Endow., Vol. 17, 10 (2024). https:\/\/www.vldb.org\/pvldb\/vol17\/p2514-li.pdf"},{"key":"e_1_3_2_1_228_1","unstructured":"Yutao Zhu et al. 2023. Large language models for information retrieval: A survey. arXiv:2308.07107(2023)."},{"key":"e_1_3_2_1_229_1","doi-asserted-by":"crossref","unstructured":"Yuqi Zhu et al. 2024. LLMs for knowledge graph construction and reasoning: recent capabilities and future opportunities. WWW(2024).","DOI":"10.1007\/s11280-024-01297-w"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3736557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:56:37Z","timestamp":1777571797000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3736557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":229,"alternative-id":["10.1145\/3711896.3736557","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3736557","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}